Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    strings of code-related characters and syntax

    oai_token-act-pair · gpt-3.5-turbo

    quotations or dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Archdemon
    -0.79
    âĹ¼
    -0.78
    ensen
    -0.74
    nown
    -0.73
     Gott
    -0.69
     Alchemist
    -0.64
     Flore
    -0.61
    ̶
    -0.61
     Bach
    -0.61
    STE
    -0.61
    POSITIVE LOGITS
    Interstitial
    1.26
    taboola
    0.96
    MpServer
    0.94
     ',
    0.80
     '.
    0.77
    ructose
    0.76
    avez
    0.73
    tis
    0.71
    ieri
    0.70
    neath
    0.69
    Act Density 0.037%

    No Known Activations